14-Day Curriculum
Each day bridges a software engineering concept to its AI equivalent.
Week 1Think Like an AI Engineer
LLM APIs, Structured Output & Streaming
You already call REST APIs and parse JSON. Today you'll call LLM APIs the same way — but you'll also learn the two killer features every AI app needs: extracting typed JSON from LLMs (structured output) and streaming responses in real-time. By tonight, you'll ship a code review tool you'll actually use at work.
Ship: AI code review tool
Embeddings & Vector Search
SQL LIKE matches characters. Vector search matches meaning. You'll learn how embeddings turn text into numbers, build similarity search from scratch, and understand when to use Pinecone, pgvector, or Chroma. You'll ship a search engine that finds 'cozy sneakers' when users type 'comfortable shoes'.
Ship: Semantic search engine
RAG Deep Dive
RAG is the #1 AI pattern in production. You'll go far beyond basics — learn multiple chunking strategies, debug retrieval failures, handle the #1 cause of hallucination (bad retrieval), and build a Q&A system that cites its sources. This is the day that separates AI engineers from tutorial followers.
Ship: Document Q&A system
Function Calling & Tool Chains
You define REST endpoints with schemas. Function calling is the same — you define tools with Zod schemas and the LLM decides when to call them. Today you'll go beyond single tool calls: parallel execution, error recovery, and multi-step tool chains where one tool's output feeds another.
Ship: AI assistant with live tools
AI Agents & Orchestration
State machines have predefined transitions. Agents decide autonomously. You'll implement multiple agent patterns (ReAct, plan-and-execute, tool-use), add safety guardrails against infinite loops and cost runaway, and build a research agent that gathers, summarizes, and compares information.
Ship: Research automation agent
Multimodal AI & Streaming UX
You handle file uploads. Now you'll make AI understand them — extracting structured JSON from images, analyzing documents, and processing audio. Plus, you'll master the UX patterns that make AI apps feel magical: streaming responses, optimistic UI, and progressive loading.
Ship: Receipt scanner + streaming chat
Capstone: AI Documentation Assistant
Combine everything from Week 1 into a real AI product: an AI documentation assistant. It uses RAG to answer questions from docs, tools to search and navigate, streaming for real-time UX, and structured output for formatted responses. This is your first portfolio-grade AI project.
Ship: AI docs assistant (portfolio piece)
Week 2Ship Like an AI Engineer
AI Evaluation & Testing
Unit tests check exact outputs. LLMs are non-deterministic — same input, different output every time. You need evals: automated quality checks using rubrics, LLM-as-judge, and eval datasets. You'll learn eval-driven development — write evals first, then iterate prompts to pass them.
Ship: Eval suite for your RAG app
Security & Guardrails
Prompt injection is SQL injection 2.0. You'll build defense-in-depth: input sanitization, structured prompts, output validation, PII detection, and content filtering. Then you'll try to break your own Day 7 capstone — because if you can't hack it, someone else will.
Ship: Hardened AI endpoint
Cost Optimization & Multi-Model Strategy
AI API costs can explode overnight. You'll learn the same cost controls you use for infrastructure — caching, routing, and optimization — adapted for AI. Semantic caching, model routing (fast/cheap vs slow/smart), multi-model strategy (GPT-4o vs Claude vs open-source), and token optimization.
Ship: Multi-model router with caching
LLMOps & Observability
You use APM to monitor APIs. LLMOps adds AI-specific observability: prompt tracing, token usage tracking, latency per model, quality scores, and cost dashboards. You'll integrate real tools (Langfuse) and learn what to log, trace, and alert on in production AI systems.
Ship: Observable AI pipeline
Fine-tuning & Model Customization
When should you fine-tune vs prompt-engineer vs use RAG? Most teams get this wrong. You'll build the decision framework, then practice each approach: optimize prompts first (cheap), add RAG for domain knowledge (medium), and fine-tune only when needed (expensive). By the end you'll know exactly which tool to reach for.
Ship: Decision framework + fine-tuned classifier
Adding AI to Existing Apps
The #1 question devs ask: 'I have an existing app — how do I add AI?' Today you'll learn the patterns: AI-powered search, smart autocomplete, content generation, automated tagging, and intelligent routing. You'll take a standard Next.js CRUD app and add 3 AI features without rewriting anything.
Ship: AI features in an existing Next.js app
Capstone: AI Codebase Q&A
Build your portfolio centerpiece: an AI-powered codebase Q&A tool. It indexes a GitHub repo, answers questions about the code using RAG, includes evals for quality, guard rails for safety, observability for monitoring, and multi-model routing for cost control. This is the project that gets you hired.
Ship: AI codebase Q&A (portfolio centerpiece)